Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world datasets and workflows.

An interpretable framework for inferring nonlinear multivariate Granger causality based on self-explaining neural networks.

Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.

A list of research papers of explainable machine learning.

An interpretable early-warning engine that detects academic instability before grades collapse. Instead of predicting performance, it models pressure accumulation, buffer strength, and transition risk using attendance, engagement, and study load to explain fragility and identify high-leverage interventions.

A systems-thinking essay that reframes failure as a gradual transition rather than a discrete outcome. It explains how pressure accumulation, weakening buffers, and hidden instability precede visible collapse, and why prediction-based models arrive too late to prevent failure in human-centered systems.

An interpretable system that models the future of work as an equilibrium under AI-driven forces. Instead of predicting job loss, it decomposes workforce disruption into automation pressure, adaptability, skill transferability, demand, and AI augmentation to explain stability, tension, and transition paths by 2030.

An analytical essay on why prediction-based models fail in reflexive, unstable systems. This article argues that accuracy collapses when models influence behavior, and proposes equilibrium and force-based modeling as a more robust framework for understanding pressure, instability, and transitions in AI-shaped systems.

Code for Surgical Skill Assessment via Video Semantic Aggregation (MICCAI 2022)

Comprehensible Convolutional Neural Networks via Guided Concept Learning

Explainable Boosting Machines

A Python implementation of Word Mover's Distance that decomposes document level WMD into word level WMD for interpretable sociocultural NLP.

🤖 Analyze the future of work with the Workforce Disruption Equilibrium Engine, a system for understanding job changes in an AI-driven world.

Reference implementation of an interpretable two-sided multicriteria model for candidate-vacancy matching

📊 Detect academic fragility early with this analytics engine that identifies instability before grades reveal the problem.

🔄 Transform failure into an opportunity for growth in analytics and system design by focusing on transitions rather than outcomes.